An adaptive deblurring method based on a Multiplicative Multiresolution Decomposition (MMD)

Author

Kerouh, Fatma ; Serir, Amina

Author_Institution

Fac. d´Electron. et d´Inf., U.S.T.H.B., Algiers, Algeria

fYear

2013

fDate

10-12 June 2013

Firstpage

88

Lastpage

93

Abstract

In this paper, a new adaptive automatic deblurring method based on the Multiplicative Multiresolution Decomposition (MMD) is proposed. It is based on the MMD coefficient variation analysis at different resolutions. An iterative deblurring process based on this analysis and controlled by a no reference image quality metric is then proposed. The image is restored by minimizing the amount of the residual blur at each iteration. The performance of the proposed method is evaluated on blurred images from the Live database. The method is compared to some known techniques. The obtained results demonstrate the effectiveness of the use of the MMD for image deblurring.

Keywords

image resolution; image restoration; iterative methods; visual databases; Live database; MMD coefficient variation analysis; adaptive automatic image deblurring method; image restoration; iterative deblurring process; multiplicative multiresolution decomposition; no reference image quality metric; residual blur minimization; Image edge detection; Image quality; Image resolution; Image restoration; Nonlinear filters; PSNR; Transforms; Blur; Multiplicative Multiresolution Decomposition (MMD); deblurring; quality measure;

fLanguage

English

Publisher

ieee

Conference_Titel

Visual Information Processing (EUVIP), 2013 4th European Workshop on

Conference_Location

Paris

Type

conf

Filename

6623957